论文标题
通过原始Circmpillary OCT图像分析手工制作和自动奖学的特征用于青光眼检测的特征
Analysis of Hand-Crafted and Automatic-Learned Features for Glaucoma Detection Through Raw Circmpapillary OCT Images
论文作者
论文摘要
考虑到青光眼是全球失明的主要原因，我们在本文中提出了青光眼检测的三种不同的学习方法，以阐明传统的机器学习技术可以优于深度学习算法，尤其是当图像数据集很小时。实验是在由专家眼科医生诊断的194个青光眼和198个正常B扫描的私人数据库上进行的。作为一种新颖性，我们仅考虑了原始的圆形电路OCT图像来构建预测模型，而无需使用其他昂贵的测试，例如视场和眼内压力测量。结果批准了基于新颖描述符的提议的手动学习模型优于自动学习。此外，由两种策略组合组合的混合方法都报告了最佳性能，在ROC曲线下的面积为0.85，在预测阶段的精度为0.82。
Taking into account that glaucoma is the leading cause of blindness worldwide, we propose in this paper three different learning methodologies for glaucoma detection in order to elucidate that traditional machine-learning techniques could outperform deep-learning algorithms, especially when the image data set is small. The experiments were performed on a private database composed of 194 glaucomatous and 198 normal B-scans diagnosed by expert ophthalmologists. As a novelty, we only considered raw circumpapillary OCT images to build the predictive models, without using other expensive tests such as visual field and intraocular pressure measures. The results ratify that the proposed hand-driven learning model, based on novel descriptors, outperforms the automatic learning. Additionally, the hybrid approach consisting of a combination of both strategies reports the best performance, with an area under the ROC curve of 0.85 and an accuracy of 0.82 during the prediction stage.
